DSPNet: Deep scale purifier network for dense crowd counting

作者：

Highlights：

• A novel counting model for dense crowd scene is proposed.

• We present a scale purifier module to decrease contextual information loss.

• Results clearly show that our method outperforms various state-of-the-art methods.

• Cross-scene evaluation verifies the high generalization ability of our model.

摘要

•A novel counting model for dense crowd scene is proposed.•We present a scale purifier module to decrease contextual information loss.•Results clearly show that our method outperforms various state-of-the-art methods.•Cross-scene evaluation verifies the high generalization ability of our model.

论文关键词：Crowd counting,Density map estimation,Convolutional neural network,Deep learning

论文评审过程：Received 17 April 2019, Revised 17 September 2019, Accepted 24 September 2019, Available online 25 September 2019, Version of Record 2 October 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112977